CN116757442B

CN116757442B - Method and system for constructing user portraits of complex electricity behavior based on current limiting algorithm

Info

Publication number: CN116757442B
Application number: CN202310999629.0A
Authority: CN
Inventors: 郭大琦; 张杨; 李红; 夏霖; 李乃一; 马闯; 陈奕; 洪潇; 何岳昊; 陆涛; 胡琰; 叶笑朗; 徐成司; 吕思源; 武宽
Original assignee: State Grid Zhejiang Electric Power Co Ltd; Hangzhou Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Current assignee: State Grid Zhejiang Electric Power Co Ltd; Hangzhou Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority date: 2023-08-09
Filing date: 2023-08-09
Publication date: 2023-10-24
Anticipated expiration: 2043-08-09
Also published as: CN116757442A

Abstract

The invention discloses a user portrait construction method and a system for complex electricity behavior based on a current limiting algorithm, comprising the following steps: s1, acquiring a first effective index of a power consumption entity to construct a power consumption entity portrait; s2, acquiring a second effective index of the power supply entity to construct a power supply entity portrait; s3, acquiring a preferred service entity set based on the service priority of the power supply entity; s4, acquiring a preferred consumption entity set based on the consumption priority of the power consumption entity; s5, acquiring an adjustable power supply allowance and an electric energy demand; s6, obtaining an adjustable power consumption entity set based on the electric energy demand and the preferred consumption entity set; s7, obtaining an adjustable power supply entity set based on the adjustable power supply margin and the preferable service entity set; s8, acquiring electricity utilization behavior association portraits of all entities in the adjustable power supply entity set and the adjustable power consumption entity set based on a current limiting algorithm. According to the invention, the supply and demand relation of the electric power entity is analyzed to describe the association portraits of the complex electricity utilization behaviors among the entities, so that the fine management and the optimal control of the electricity utilization behaviors are realized.

Description

Method and system for constructing user portraits of complex electricity behavior based on current limiting algorithm

Technical Field

The invention relates to the technical field of data analysis, in particular to a user portrait construction method and a system for complex electricity behavior based on a current limiting algorithm.

Background

In modern society, power demand is increasing, and power system supply and demand balance and power load management are becoming particularly important. In particular, the popularity of electric vehicles has accelerated the need for charging equipment, particularly sharing charging posts. The traditional charging pile load management method is often only considered from the point of view of overall load, and the careful understanding of the electricity utilization behaviors of individual users is lacking. Because the charging characteristics of the power supply entity (electric automobile) have randomness and uncertainty, the power supply of the power supply entity (charging pile) is limited by the load factor constraint of the platform area; therefore, the existence of the complicated electricity consumption behavior users makes the management of the electric power system face greater challenges, how to balance the supply and demand balance between the power supply entities and the power consumption entities, ensure the electricity consumption safety of the platform area, and a set of method for describing the user portraits of the complicated electricity consumption behaviors needs to be designed, so that the complicated electricity consumption behaviors existing between each power supply entity and each power consumption entity are analyzed, the electricity consumption behaviors of each power entity are further stimulated and standardized, and the stable operation of the electric power system is ensured.

Chinese patent, publication No.: CN115168437a, publication date: 2022, 10 and 11, discloses a method and a system for realizing electricity user portrayal based on data analysis, wherein the method comprises the following steps: step 1: collecting historical electricity utilization data of a user, and pre-classifying the historical electricity utilization data to obtain a plurality of types of electricity utilization data; step 2: constructing initial electricity utilization behaviors of each type of electricity utilization data, and setting an electricity utilization label for each initial electricity utilization behavior; step 3: extracting representative electricity behaviors from all initial electricity behaviors based on the label setting result; step 4: and constructing a user electricity consumption image of the user based on the representative electricity consumption behavior. Through setting up the electricity consumption label to user's electricity consumption action to draw representative electricity consumption action, and then construct user's electricity consumption image, be convenient for accurate locking user's electricity demand, the accurate recommendation of follow-up power consumption condition of indirect convenience for the user. In the scheme, only the requirement of the power utilization end is analyzed, the requirement of the power supply end is not analyzed, the influence of complex power utilization behaviors between the power supply entity and the power utilization entity on the safe operation of the power system is not considered, and the power utilization behaviors cannot be further standardized and stimulated.

The above information disclosed in the background section is only for enhancement of understanding of the background of the application and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art.

Disclosure of Invention

Aiming at the problem that the management of power supply and demand is difficult due to the lack of analysis of complex power consumption behaviors, the application provides a current limiting algorithm-based complex power consumption behavior user portrait construction method and system.

In a first aspect, a technical solution provided in an embodiment of the present application is: the method for constructing the user portrait of the complex electricity consumption behavior based on the current limiting algorithm comprises the following steps:

s1, acquiring power consumption entity characteristic data on a long-time domain of a station area, calculating first information value degrees between each characteristic index and a first characteristic variable in a power consumption entity, taking the characteristic index with the first information value degree being larger than a set association threshold H1 as a first effective index, and constructing a power consumption entity portrait of the characteristic variable based on the first effective index;

S2, acquiring power supply entity characteristic data on a long-time domain of a station area, calculating second information value degrees between each characteristic index and a second characteristic variable in a power supply entity, taking the characteristic index with the second information value degree being larger than a set association threshold H2 as a second effective index, and constructing a power supply entity portrait of the characteristic variable based on the second effective index;

s3, constructing a first association degree set with each power supply entity in the platform area based on a consumption path of the power consumption entity; integrating the first association degree set based on the service priority of the power supply entity to obtain a preferred service entity set;

s4, constructing a second association degree set of each power consumption entity in the platform area based on the service path of the power supply entity; integrating the second association degree set based on the consumption priority of the power consumption entity to obtain a preferred consumption entity set;

s5, acquiring an adjustable power supply allowance and an electric energy demand on a time-sharing time scale;

s6, obtaining an adjustable power consumption entity set based on the electric energy demand and the preferred consumption entity set;

s7, obtaining an adjustable power supply entity set based on the adjustable power supply margin and the preferable service entity set;

and S8, calibrating the chargeable time domain based on a current limiting algorithm, and acquiring electricity utilization behavior association figures of all entities in the adjustable power supply entity set and the adjustable power consumption entity set based on a calibration result.

In the scheme, characteristic data of each power consumption entity is firstly analyzed, characteristic data affecting consumption behaviors of the power consumption entity are obtained to serve as first effective indexes, a power consumption entity portrait can be constructed based on the first effective indexes, characteristic variables of the power consumption entity are output result data based on a logistic regression model, and the result is divided into two types: an inactive power consuming entity and an active power consuming entity; wherein the inactive power consuming entity and the active power consuming entity are partitioned based on a charging probability behavior of the power consuming entity; similarly, the characteristic data of each power supply entity is analyzed, the characteristic data affecting the service behavior of the power supply entity is obtained to serve as a second effective index, a power supply entity portrait can be constructed based on the second effective index, the characteristic variables of the power supply entity are result data output based on a logistic regression model, and the result is divided into two types: an inactive power supply entity and an active power supply entity; wherein the inactive power supply entity and the active power supply entity are divided based on the power supply probability of the power consuming entity; further, the consumption path of the power consumption entity is analyzed, so that the consumption habit of the power consumption entity can be further analyzed, and the association relationship between the power consumption entity and the power supply entity is established; similarly, the service path of the power supply entity is analyzed, so that the service habit of the power supply entity can be further analyzed, and the association relationship between the power supply entity and the power consumption entity is established; providing reference data for subsequent resource pairing; then analyzing the adjustable power supply allowance and the electric energy demand on each time-sharing time scale, and selecting the optimal power supply entity and power consumption entity combination based on the electric power supply and demand relation; finally, considering the problem of unbalance of power supply and power demand on a time-sharing time scale, calibrating a chargeable time domain based on a current limiting algorithm, and acquiring power consumption behavior association images of each entity in an adjustable power supply entity set and an adjustable power consumption entity set based on a calibration result, so that each power supply entity and each power supply entity can form an optimal power supply and demand combination, and the management and control efficiency and stability of a power system are further improved while the fine management and optimization control of the power consumption behaviors are realized.

Preferably, the method for obtaining the characteristic data of the power consumption entity in the long-time domain of the station area, calculating a first information value degree between each characteristic index and a first characteristic variable in the power consumption entity, using the characteristic index with the first information value degree larger than a set association threshold H1 as a first effective index, and constructing the power consumption entity representation of the characteristic variable based on the first effective index, includes the following steps:

s11, taking the power consumption entity state information as a tag item and the power consumption entity attribute information and public transformer liability characteristic information as a characteristic item;

s12, respectively calculating first information value degrees between index data corresponding to each characteristic item and the tag items, taking the characteristic index larger than the association threshold H1 as a first effective index, and constructing a logistic regression model based on the first effective index;

s13, calculating the association coefficient of the charging probability of each power consumption entity and the corresponding first effective index based on a logistic regression model;

s14, constructing a power consumption entity portrait based on the charging probability of the power consumption entity and the association coefficient of the corresponding first effective index.

In the scheme, the state information of the power consumption entity is used as a tag item, wherein the tag item comprises an inactive power consumption entity and an active power consumption entity; the method comprises the steps that the index is screened by calculating the information value (IV index) of the index corresponding to each characteristic item, wherein the IV index is used for measuring the relevance between two classified variables, one of the two classified variables is a binary variable, the lower the IV value is, the weaker the predictive power of the index is, the lower the relevance is, otherwise, the index has strong relevance with a result variable, the strong relevance index can be screened through an IV index predictive power table, and when the IV value is larger than a relevance threshold H1 (for example, H1=0.3), the index has strong relevance with the result variable; the index with the largest relevance to the result variable can be selected as the input variable of the logistic regression model, wherein the first effective index is constructed based on the index with the largest relevance to the result variable, and the calculation method and the application scene of the information value degree are not described in detail; further, the charging probability of each power consumption entity is output through a logistic regression model, and a contribution rate coefficient (association coefficient) corresponding to each effective index can be obtained based on a probability formula; and the association coefficient between the charging probability of the power consumption entity and the corresponding first effective index constructs a power consumption entity portrait, and the association relation between the charging behavior and each index can be intuitively analyzed through the power consumption entity portrait.

Preferably, the obtaining the power supply entity characteristic data on the long-time domain of the station area, calculating a second information value degree between each characteristic index and a second characteristic variable in the power supply entity, taking the characteristic index with the second information value degree being greater than a set association threshold H2 as a second effective index, and constructing a power supply entity portrait of the characteristic variable based on the second effective index, including the following steps:

s21, using the state information of the power supply entity as a tag item, and using the attribute information of the power supply entity and the public variable liability characteristic information as a characteristic item;

s22, respectively calculating second information value degrees between index data corresponding to each characteristic item and the tag items, taking the characteristic index larger than the association threshold H2 as a first effective index, and constructing a logistic regression model based on the second effective index;

s23, calculating the association coefficient of the power supply probability of each power supply entity and the corresponding second effective index based on the logistic regression model;

s24, constructing a power supply entity portrait based on the power supply probability of the power supply entity and the association coefficient of the corresponding second effective index.

In the scheme, the state information of the power supply entity is used as a tag item, wherein the tag item comprises an inactive power supply entity and an active power supply entity; the method comprises the steps that the index is screened by calculating the information value (IV index) of the index corresponding to each characteristic item, wherein the IV index is used for measuring the relevance between two classified variables, one of the two classified variables is a binary variable, the lower the IV value is, the weaker the predictive power of the index is, the lower the relevance is, otherwise, the index has strong relevance with a result variable, the strong relevance index can be screened through an IV index predictive power table, and when the IV value is larger than a relevance threshold H2 (for example, H2=0.3), the index has strong relevance with the result variable; the index with the largest relevance to the result variable can be selected as the input variable of the logistic regression model, wherein the first effective index is constructed based on the index with the largest relevance to the result variable, and the calculation method and the application scene of the information value degree are not described in detail; further, the power supply probability of each power supply entity is output through a logistic regression model, and a contribution rate coefficient (association coefficient) corresponding to each effective index can be obtained based on a probability formula; the power supply entity image is constructed by the power supply probability of the power supply entity and the association coefficient of the corresponding second effective index, and the association relation between the power supply behavior and each index can be intuitively analyzed through the power supply entity image.

Preferably, the consumption path based on the power consumption entity constructs a first association degree set with each power supply entity in the platform area; integrating the first association degree set based on the service priority of the power supply entity to obtain a preferred service entity set, comprising the following steps:

s31, acquiring a corresponding target power supply entity based on a link relation between a power consumption entity and the power supply entity in a long time domain to construct a first association set;

s32, respectively calculating first link degrees of the power consumption entity and each target power supply entity, and taking the first link degrees as an evaluation index of the service priority;

and S33, sorting all the target power supply entities in the first association degree set from large to small based on the service priority to obtain a preferred service entity set.

In the scheme, a first association set is obtained by selecting a link relation between each power consumption entity and a power supply entity in a long time domain (the long time domain can be a month unit or a year unit), wherein the first association set comprises a plurality of power supply entities which have a link relation with the current power consumption entity; respectively calculating a first linking degree of the power consumption entity and each target power supply entity, and taking the first linking degree as an evaluation index of the service priority, wherein the higher the linking degree is, the higher the probability that the power consumption entity selects the power supply entity to implement charging behavior is; and sequencing all the target power supply entities in the first association degree set from large to small based on the service priority to obtain a preferred service entity set.

Preferably, the first linking degree L1 is calculated by the following formula:

L1=P1/T1

wherein P1 represents the total charging power linked to the current target power supply entity; t1 is the total number of links with the current target power entity.

In the scheme, the link degree is measured by adopting the ratio of the total charging power of the link of the target power supply entity to the total link times of the target power supply entity, so that the power utilization habit of each power consumption entity can be further reflected.

Preferably, the service path based on the power supply entity constructs a second association degree set with each power consumption entity in the platform area; integrating the second association degree set based on the consumption priority of the power consumption entity to obtain a preferred consumption entity set, comprising the following steps:

s41, acquiring a corresponding target power consumption entity based on a link relation between a power supply entity and the power consumption entity in a long time domain to construct a second association set;

s42, respectively calculating second link degrees of the power supply entity and each target power consumption entity, and taking the second link degrees as an evaluation index of the consumption priority;

s43, sorting all target power consumption entities in the second association degree set from large to small based on the consumption priority to obtain a preferred consumption entity set.

In the scheme, a second association set is obtained by selecting the link relation between each power supply entity and the power consumption entity in a long time domain (the long time domain can be a month unit or a year unit), wherein the second association set comprises a plurality of power consumption entities with link relation with the current power supply entity; respectively calculating a second linking degree of the power supply entity and each target power consumption entity, and taking the second linking degree as an evaluation index of the consumption priority, wherein the higher the linking degree is, the higher the probability that the power supply entity provides charging service behaviors for the current power supply entity is; and sequencing all the target power supply entities in the second association degree set from large to small based on the service priority to obtain a preferred service entity set.

Preferably, the second link degree L2 is calculated by the following formula:

L2=P2/T2

wherein P2 represents the total discharge power linked to the current target power consuming entity; t2 is the total number of links with the current target power consuming entity.

In the scheme, the link degree is measured by adopting the ratio of the total discharge power of the link of the target power consumption entity to the total link times of the target power consumption entity, so that the power utilization habit of each power supply entity can be further reflected.

Preferably, the obtaining the adjustable power supply margin and the electric energy demand on the time-sharing time scale comprises the following steps:

s51, carrying out time-interval cutting on a long time domain based on a power time-sharing price adjustment rule to obtain a time-sharing time scale;

s52, acquiring a public variable load occupancy on each time-sharing time scale; acquiring an adjustable power supply allowance based on a public variable load occupancy;

synchronously, power consumption entities with the charging probability larger than a set threshold H3 on each time-sharing time scale are obtained, and the total charging power of the power consumption entities on the time-sharing time scale is taken as the electric energy demand.

In the scheme, because the electricity prices of different time periods are different, the time domain is cut based on the different electricity prices to obtain a time-sharing time scale; acquiring an adjustable power supply margin based on a public variable load occupancy on a current time-sharing time scale, wherein it can be understood that when the rated capacity of the transformer in the transformer area is 100kVA; the actual capacity is 65kVA; when the occupancy of the public variable load is 65%, the adjustable power supply margin is 35 kVA; further, all the power consumption entities on the time-sharing time scale are obtained based on the power consumption habit of the power consumption entity, the power consumption entity with the charging probability larger than the set threshold H3 (for example, h3=0.1) is selected as the effective power consumption entity, the total charging power on the time-sharing time scale is calculated as the electric energy demand, and it is understood that when the charging probability is smaller than the set threshold H3, the power consumption entity has no charging behavior, no behavior participating in electric energy consumption, and the power consumption entity can be removed, so that the data can be further thinned, and the analysis efficiency is improved.

Preferably, the obtaining the adjustable power consumption entity set based on the power demand and the preferred consumption entity set includes the following steps:

s61, acquiring an optimal power combination of the power consumption entities based on the electric energy demand, and acquiring a target power consumption entity corresponding to the optimal power combination in the optimal power consumption entity set to construct an adjustable power consumption entity set.

In the scheme, because the electric energy requirement of each power consumption entity is different and the electric energy requirement in the current period is certain, in order to fully utilize the electric energy requirement in the current period and improve the electric energy utilization efficiency, an optimal power combination needs to be established, and the electric energy requirement is used as a power constraint; and selecting all target power consumption entities participating in current power consumption to construct an adjustable power consumption entity set.

Preferably, the obtaining the set of adjustable power supply entities based on the adjustable power supply margin and the set of preferred service entities includes the following steps:

s71, acquiring an optimal power combination of the power supply entity based on the adjustable power supply margin, and acquiring a target power supply entity corresponding to the optimal power combination in the optimal service entity set to construct an adjustable power supply entity set.

In the scheme, since the power supply power of each power supply entity is different and the adjustable power supply allowance in the current period is certain, in order to fully utilize the maximum power supply amount in the current period and improve the electric energy utilization efficiency, an optimal power combination needs to be built, and the adjustable power supply allowance is adopted as the power constraint; and selecting all target power supply entities participating in the current power service to construct an adjustable power supply entity set.

Preferably, the calibrating the chargeable time domain based on the current limiting algorithm, and acquiring the electricity consumption behavior association image of each entity in the adjustable power supply entity set and the adjustable electricity consumption entity set based on the calibrating result, includes the following steps:

s801, acquiring an adjustable power supply entity set on each time scale, and sequentially acquiring target power supply entities with the same discharge power in each adjustable power supply entity set to construct a first flow container;

s802, prioritizing the time scales of the split time from low to high based on electricity prices to obtain a first optimal calibration time table;

s803, acquiring a target power consumption entity matched with the discharge power in the adjustable power consumption entity set based on the flow boundary of the first flow container;

s804, sequentially selecting target power supply entities in a time-sharing time scale of the corresponding priority in the first preferential calibration time table based on the consumption priority of the target power consumption entity for linking;

s805, executing S801-S804 based on a current limiting algorithm, and sequentially acquiring electricity consumption behavior association figures of a target power supply entity and a target power consumption entity.

In the scheme, target power supply entities with the same discharge power on each time scale are sequentially screened out to construct a first flow container, and the boundary of the first flow container is known as the maximum discharge power on the time scale; because different electricity prices have different excitation effects on different electricity consumption entities, the time-sharing time scales are prioritized to obtain a first optimal calibration time table, and it can be understood that the electricity consumption entity with better electricity consumption behavior (user activity) is preferentially scheduled to a time scale interval with lower electricity price for charging behavior, so that the electricity consumption entity can be effectively excited to normalize the own electricity consumption behavior (for example, the single charging electric quantity can be improved, the time interval of the lifting time can be shortened, and the user activity can be improved); and the flow boundary of the first flow container is used as a charging constraint condition, the target power consumption entity of the discharging power is matched, and finally, a corresponding power supply entity and a charging time scale interval are selected for each power consumption entity, so that the power consumption behavior of the power entity is indirectly standardized and positively stimulated while the fine management and the optimal control of the power consumption behavior are realized.

Preferably, the calibrating the chargeable time domain based on the current limiting algorithm obtains the electricity consumption behavior association portrait of each entity in the adjustable power supply entity set and the adjustable power consumption entity set based on the calibrating result, and the method further comprises the following steps:

s811, acquiring an adjustable power consumption entity set on each time scale, and sequentially acquiring target power consumption entities with the same charging power in each adjustable power consumption entity set to construct a second flow container;

s812, prioritizing the time scales of the split time from high to low based on electricity prices to obtain a second optimal calibration time table;

s813, acquiring a target power supply entity matched with the charging power in the adjustable power supply entity set based on the flow boundary of the second flow container;

s814, sequentially selecting target power consumption entities in a time-sharing time scale of the corresponding priority in the first preferential calibration time table based on the service priority of the target power supply entity for linking;

s815, executing S811-S814 based on a current limiting algorithm, and sequentially acquiring electricity consumption behavior association figures of the target electricity consumption entity and the target power supply entity.

In the scheme, target power consumption entities with the same charging power on each time scale are sequentially screened out to construct a second flow container, and the boundary of the second flow container is known as the maximum charging power on the time scale; because different electricity prices have different excitation effects on different power supply entities, the time-sharing time scales are prioritized to obtain a second optimal calibration time table, and it can be understood that the power supply entities with better electricity consumption behavior (user activity) are preferentially scheduled to a time scale interval with higher electricity prices to perform discharging behavior, and because the power supply entities possibly belong to different service providers, the service policies of the different service providers are different, the service providers can be effectively stimulated to optimize the own electricity consumption behavior (for example, the single power supply electric quantity can be improved, the power supply time interval can be shortened, and the user activity can be improved); and the flow boundary of the second flow container is used as a power supply constraint condition, a target power supply entity of discharge power is matched, and a corresponding power consumption entity and a discharge time scale interval are selected for each power consumption entity, so that the power consumption behavior of the power entity is indirectly standardized and positively stimulated while the fine management and the optimal control of the power consumption behavior are realized.

Preferably, the current limiting algorithm is one of a sliding window current limiting algorithm, a leaky bucket current limiting algorithm and a token bucket current limiting algorithm.

In the scheme, in daily charging service, because the charging of the electric automobile has randomness, when sudden situations such as electricity consumption peak period exist, the charging amount is greatly increased, and in order to ensure the safety of electric power operation, the electricity consumption behavior of an electric entity with high charging and discharging priority (high activity degree) is ensured, so that current limitation is needed; for example, according to the maximum discharge power of the first flow container or the maximum charge power of the second flow container, a current limiting algorithm may be adopted, when the charge power of all the target power consumption entities is greater than the maximum discharge power, the current target power consumption entities may be sequentially arranged to the time scale interval of the next priority for performing the charging action, and similarly, when the discharge power of all the target power supply entities is greater than the maximum charge power, the current target power supply entities may be sequentially arranged to the time scale interval of the next priority for performing the discharging action, so as to ensure the stability of the charging and discharging actions.

Preferably, the power consumption entity state information includes: inactive power consuming entities and active power consuming entities.

Preferably, the power consumption entity attribute information: charging period, charging duration, charging frequency, charging power, charging day, single charge power distribution, and time interval for lifting.

Preferably, the power supply entity status information includes: an inactive power entity and an active power entity.

Preferably, the power supply entity attribute information includes: the power supply system comprises a power supply period, a power supply duration, a power supply frequency, a power supply power, a power supply day, a single power supply electric quantity distribution and a power supply time interval.

Preferably, the public variable liability characteristic includes: the public transformer load ratios corresponding to the number of the charging piles and the public transformer load ratios corresponding to different seasons.

In a second aspect, a technical solution provided in the embodiments of the present invention is: a complicated electricity behavior user portrait construction system comprises:

the power consumption entity portrait construction module: acquiring power consumption entity characteristic data on a long-time domain of a station area, calculating first information value degrees between each characteristic index and a first characteristic variable in a power consumption entity, taking the characteristic index with the first information value degree being larger than a set association threshold H1 as a first effective index, and constructing a power consumption entity portrait of the characteristic variable based on the first effective index;

The power supply entity portrait construction module: acquiring power supply entity characteristic data on a long-time domain of a station area, calculating second information value degrees between each characteristic index and a second characteristic variable in a power supply entity, taking the characteristic index with the second information value degree being larger than a set association threshold H2 as a second effective index, and constructing a power supply entity portrait of the characteristic variable based on the second effective index;

a first integration module: constructing a first association degree set with each power supply entity in the platform area based on a consumption path of the power consumption entity; integrating the first association degree set based on the service priority of the power supply entity to obtain a preferred service entity set;

and a second integration module: constructing a second association degree set with each power consumption entity in the platform area based on the service path of the power supply entity; integrating the second association degree set based on the consumption priority of the power consumption entity to obtain a preferred consumption entity set;

the acquisition module is used for: acquiring an adjustable power supply allowance and an electric energy demand on a time-sharing time scale;

a first reconstruction module: obtaining an adjustable power consumption entity set based on the power demand and the preferred consumption entity set;

and a second reconstruction module: obtaining an adjustable power supply entity set based on the adjustable power supply margin and the preferred service entity set;

The associated portrait construction module: and calibrating the chargeable time domain based on a current limiting algorithm, and acquiring electricity utilization behavior association figures of all entities in the adjustable power supply entity set and the adjustable power consumption entity set based on a calibration result.

In a third aspect, a technical solution provided in an embodiment of the present invention is: an electronic device comprising a memory and a processor, said memory having stored therein a computer program, said processor implementing the steps of the complex electricity usage behavior user portrayal construction method based on the current limiting algorithm when invoking the computer program in said memory.

In a fourth aspect, the present invention provides a technical solution, which is: a storage medium having stored therein computer executable instructions which, when loaded and executed by a processor, implement the steps of the complex electricity usage behavior user portrayal construction method based on a current limiting algorithm as described.

The invention discloses a user portrait construction method and a system for complex electricity behavior based on a current limiting algorithm, which have at least the following substantial beneficial effects.

(1) By carrying out association analysis on the power consumption entity and the power supply entity in a long time domain, the supply and demand relation between each power consumption entity and each power supply entity is more comprehensively and deeply known, the complex power consumption behavior association portraits among the entities are depicted, the fine management and the optimized control of the power consumption behaviors are realized, and therefore the management and control efficiency and the stability of a power system are improved.

(2) Considering that different electricity prices have different excitation effects on different electricity consumption entities, the time-sharing time scales are prioritized to obtain a first optimal calibration time table, and the electricity consumption entity with better electricity consumption behavior (user activity) is preferentially scheduled to a time scale interval with lower electricity price for charging behavior, so that the electricity consumption entity can be effectively excited to normalize the electricity consumption behavior of the electricity consumption entity (for example, the single charging electric quantity can be improved, the time interval of the lifting time can be shortened, and the user activity can be improved); and the flow boundary of the first flow container is used as a charging constraint condition, the target power consumption entity of the discharging power is matched, and finally, a corresponding power supply entity and a charging time scale interval are selected for each power consumption entity, so that the power consumption behavior of the power entity is indirectly standardized and positively stimulated while the fine management and the optimal control of the power consumption behavior are realized.

(3) Considering that different electricity prices have different excitation effects on different power supply entities, the time-sharing time scales are prioritized to obtain a second optimal calibration time table, and the power supply entity with better electricity consumption behavior (user activity) is preferentially scheduled to a time scale interval with higher electricity prices for discharging, and because the power supply entity possibly belongs to different service providers, the service policies of the different service providers are different, the service providers can be effectively stimulated to optimize own electricity consumption behavior or service behavior (for example, single power supply electric quantity can be improved, the power supply time interval can be shortened, and the user activity can be improved); and the flow boundary of the second flow container is used as a power supply constraint condition, a target power supply entity of discharge power is matched, and a corresponding power consumption entity and a discharge time scale interval are selected for each power consumption entity, so that the power consumption behavior of the power entity is indirectly standardized and positively stimulated while the fine management and the optimal control of the power consumption behavior are realized.

(4) In daily charging business, because the charging of the electric automobile has randomness, when sudden situations such as electricity consumption peak period exist, the charging amount is greatly increased, and in order to ensure the safety of electric power operation, the electricity consumption behavior of an electric entity with high charging and discharging priority (high activity level) is ensured, so that current limitation is needed; for example, according to the maximum discharge power of the first flow container or the maximum charge power of the second flow container, a current limiting algorithm may be adopted, and when the charge power of all the target power consumption entities is greater than the maximum discharge power, the current target power consumption entities may be sequentially arranged to the time scale interval of the next priority for performing the charging action. Similarly, when the discharge power of all the target power supply entities is greater than the maximum charge power, the current target power supply entity can be sequentially arranged to a time scale interval of the next priority for carrying out discharge behaviors, so that the method can adapt to real-time power supply and demand conditions and user power demand characteristics and ensure the stability of the charge and discharge behaviors.

The foregoing summary is merely an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more fully understood, and in order that the same or additional objects, features and advantages of the present invention may be more fully understood.

Drawings

Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures.

FIG. 1 is a flow chart of the user portrayal construction method of the complex electricity behavior based on the current limiting algorithm of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and examples, it being understood that the detailed description herein is merely a preferred embodiment of the present invention, which is intended to illustrate the present invention, and not to limit the scope of the invention, as all other embodiments obtained by those skilled in the art without making any inventive effort fall within the scope of the present invention.

Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts operations (or steps) as a sequential process, many of the operations (or steps) can be performed in parallel, concurrently, or at the same time. Furthermore, the order of the operations may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures; the processes may correspond to methods, functions, procedures, subroutines, and the like.

Embodiment one:

as shown in FIG. 1, the method for constructing the user portrait of the complex electricity consumption behavior based on the current limiting algorithm comprises the following steps:

s1, acquiring power consumption entity characteristic data on a long-time domain of a station area, calculating first information value degrees between each characteristic index and a first characteristic variable in power consumption entities, taking the characteristic index with the first information value degree being larger than a set association threshold H1 as a first effective index, and constructing a power consumption entity portrait of the characteristic variable based on the first effective index.

Specifically, S1 includes the steps of:

Specifically, the power consumption entity state information is used as a tag item, wherein the tag item comprises an inactive power consumption entity and an active power consumption entity;

specifically, the power consumption entity attribute information includes: charging period, charging duration, charging frequency, charging power, charging day, single charge power distribution, and time interval for lifting.

Specifically, the public variable liability characteristics include: the public transformer load ratios corresponding to the number of the charging piles and the public transformer load ratios corresponding to different seasons.

It can be understood that, the index is screened by calculating the information value (IV index) of the index corresponding to each feature item, the IV index is used for measuring the relevance between two classified variables, one of the two classified variables is a binary variable, the lower the IV value is, the weaker the prediction force of the index is, and the lower the relevance is, otherwise, the index and the result variable are illustrated to have strong relevance, the IV index prediction force table is used for screening the strong relevance index, and when the IV value is greater than the relevance threshold H1 (for example, h1=0.3), the index and the result variable are indicated to have strong relevance; the index with the largest relevance to the result variable can be selected as the input variable of the logistic regression model, wherein the first effective index is constructed based on the index with the largest relevance to the result variable, and the calculation method and the application scene of the information value degree are not described in detail; further, the charging probability of each power consumption entity is output through a logistic regression model, and a contribution rate coefficient (association coefficient) corresponding to each effective index can be obtained based on a probability formula; the charging probability of the power consumption entity and the corresponding correlation coefficient of the first effective index construct a power consumption entity image, and the correlation relationship between the charging behavior and each index can be intuitively analyzed through the power consumption entity image, for example, the obtained power consumption entity image is a= [ a1, a2, a3, a4, a5, a6, a7, a8, a9, a10].

The calculation formula of the IV value is as follows:

；

wherein the method comprises the steps ofAnd->Respectively the firstiTarget variable in individual packetsyThe percentages recorded in the first and second categories, namely:

、/>；

it can be understood that in this embodiment, the data is divided into two groups, that is, the power consumption entity attribute information and the public variable liability characteristic information, and the power consumption entity attribute information is divided into seven types, specifically: charging period, charging duration, charging frequency, charging power, charging day, single charging electric quantity distribution and time interval of lifting; the public transformer liability characteristic information is divided into two types, specifically: the common variable load rate corresponding to the number of the charging piles and the common variable load rate corresponding to different seasons; and sequentially calculating IV values of various indexes through the formulas, and obtaining effective indexes through screening specifications.

It can be understood that the information value of the characteristic index of the power consumption entity is calculated by a calculation formula of the IV value; for example: charging period x1=0.452, charging duration x2=0.462, charging frequency x3=0.584, charging power x4=0.574, charging day x5=0.234, single charge power distribution x6=0.125, lifting time interval x7= 0.553; setting the IV value to be greater than the association threshold h1=0.3 indicates that the index has strong association with the result variable; it is known that the first effective index is [ x1, x2, x3, x4, x7].

S2, acquiring power supply entity characteristic data on a long-time domain of the station area, calculating second information value degrees between each characteristic index and a second characteristic variable in the power supply entity, taking the characteristic index with the second information value degrees being larger than a set association threshold H2 as a second effective index, and constructing a power supply entity portrait of the characteristic variable based on the second effective index.

Specifically, S2 includes the steps of:

Specifically, the power supply entity state information includes: an inactive power entity and an active power entity.

Specifically, the power supply entity attribute information includes: the power supply system comprises a power supply period, a power supply duration, a power supply frequency, a power supply power, a power supply day, a single power supply electric quantity distribution and a power supply time interval.

In this embodiment, the power supply entity status information is used as a tag item, where the tag item includes an inactive power supply entity and an active power supply entity; it can be understood that, the index is screened by calculating the information value (IV index) of the index corresponding to each feature item, the IV index is used for measuring the relevance between two classified variables, one of the two classified variables is a binary variable, the lower the IV value is, the weaker the prediction force of the index is, and the lower the relevance is, otherwise, the index and the result variable are illustrated to have strong relevance, the IV index prediction force table is used for screening the strong relevance index, and when the IV value is greater than the relevance threshold H2 (for example, h2=0.3), the index and the result variable are indicated to have strong relevance; the index with the largest relevance to the result variable can be selected as the input variable of the logistic regression model, wherein the first effective index is constructed based on the index with the largest relevance to the result variable, and the calculation method and the application scene of the information value degree are not described in detail; further, the power supply probability of each power supply entity is output through a logistic regression model, and a contribution rate coefficient (association coefficient) corresponding to each effective index can be obtained based on a probability formula; the power supply entity image is constructed by the power supply probability of the power supply entity and the association coefficient of the corresponding second effective index, and the association relation between the power supply behavior and each index can be intuitively analyzed through the power supply entity image, for example, the obtained power supply entity image is B= [ B1, B2, B3, B4, B5, B6, B7, B8, B9, B10].

It can be understood that the information value of the characteristic index of the power supply entity is calculated through a calculation formula of the IV value; for example: power supply period y1=0.562, power supply period y2=0.513, power supply frequency y3=0.654, power supply y4=0.552, power supply day y5=0.125, single power supply amount distribution y6=0.252, and power supply time interval y7=0.445; setting the IV value to be greater than the association threshold h1=0.3 indicates that the index has strong association with the result variable; the second effective index is known as [ y1, y2, y3, y4, y7].

S3, constructing a first association degree set with each power supply entity in the platform area based on a consumption path of the power consumption entity; and integrating the first association degree set based on the service priority of the power supply entity to obtain a preferred service entity set.

Specifically, S3 includes the steps of:

In this embodiment, a first association set is obtained by selecting a link relationship between each power consumption entity and a power supply entity in a long time domain (the long time domain may be a month unit or a year unit), where the first association set includes a plurality of power supply entities having a link relationship with a current power consumption entity, for example, in one month, the power consumption entity a1 is linked with the power supply entity b1 10 times, the power supply entity b3 5 times, the power supply entity b6 3 times, the power supply entity b8 2 times, and the power supply entity b2 1 time; respectively calculating a first linking degree of the power consumption entity and each target power supply entity, and taking the first linking degree as an evaluation index of the service priority, wherein the higher the linking degree is, the higher the probability that the power consumption entity selects the power supply entity to implement charging behavior is; and ordering all the target power supply entities in the first association degree set from large to small based on the service priority to obtain a preferred service entity set A1= [ b1, b3, b6, b8, b2].

Further, the first linking degree L1 is calculated as:

L1=P1/T1

It can be understood that the link degree is measured by adopting the ratio of the total charging power of the link of the target power supply entity to the total link number of the target power supply entity, so that the electricity utilization habit of each electricity consumption entity can be further reflected.

S4, constructing a second association degree set of each power consumption entity in the platform area based on the service path of the power supply entity; and integrating the second association degree set based on the consumption priority of the power consumption entity to obtain a preferred consumption entity set.

Specifically, S4 includes the steps of:

In this embodiment, a second association set is obtained by selecting a link relationship between each power supply entity and a power consumption entity in a long time domain (the long time domain may be a month unit, or may be a year unit), where the second association set includes a plurality of power consumption entities having a link relationship with the current power supply entity, for example, in one month, the power supply entity b1 links with the power consumption entity a1 10 times, links with the power consumption entity a3 5 times, links with the power consumption entity a6 3 times, links with the power consumption entity a8 2 times, and links with the power consumption entity a2 1 time; the method comprises the steps of carrying out a first treatment on the surface of the Respectively calculating a second linking degree of the power supply entity and each target power consumption entity, and taking the second linking degree as an evaluation index of the consumption priority, wherein the higher the linking degree is, the higher the probability that the power supply entity provides charging service behaviors for the current power supply entity is; and ordering each target power supply entity in the second association degree set from large to small based on the service priority to obtain a preferred consumption entity set B1= [ a1, a3, a6, a8, a2].

Further, the second link degree L2 has a calculation formula:

L2=P2/T2

It can be understood that the link degree is measured by adopting the ratio of the total discharge power of the link of the target power consumption entity to the total link number of the target power consumption entity, so that the power consumption habit of each power supply entity can be further reflected.

S5, acquiring an adjustable power supply allowance and an electric energy demand on a time-sharing time scale.

Specifically, S5 includes the steps of:

In the embodiment, since the electricity prices at different time periods are different, the time domain is cut based on the different electricity prices to obtain a time-sharing time scale; acquiring an adjustable power supply margin based on a public variable load occupancy on a current time-sharing time scale, wherein it can be understood that when the rated capacity of the transformer in the transformer area is 100kVA; the actual capacity is 65kVA; when the occupancy of the public variable load is 65%, the adjustable power supply margin is 35 kVA; further, all the power consumption entities on the time-sharing time scale are obtained based on the power consumption habit of the power consumption entity, the power consumption entity with the charging probability larger than the set threshold H3 (for example, h3=0.1) is selected as the effective power consumption entity, the total charging power on the time-sharing time scale is calculated as the electric energy demand, and it is understood that when the charging probability is smaller than the set threshold H3, the power consumption entity has no charging behavior, no behavior participating in electric energy consumption, and the power consumption entity can be removed, so that the data can be further thinned, and the analysis efficiency is improved.

S6, obtaining an adjustable power consumption entity set based on the electric energy demand and the preferred consumption entity set.

Specifically, S6 includes the steps of:

In this embodiment, because the electric energy requirement of each power consumption entity is different and the electric energy requirement in the current period is certain, in order to fully utilize the electric energy requirement in the current period and improve the electric energy utilization efficiency, an optimal power combination needs to be built, and the electric energy requirement is adopted as the power constraint; and selecting all target power consumption entities participating in current power consumption to construct an adjustable power consumption entity set.

S7, obtaining an adjustable power supply entity set based on the adjustable power supply margin and the preferable service entity set.

Specifically, S7 includes the steps of:

In this embodiment, since the power supply power of each power supply entity is different and the adjustable power supply margin in the current period is certain, in order to fully utilize the maximum power supply amount in the current period and improve the power utilization efficiency, an optimal power combination needs to be built, and the adjustable power supply margin is adopted as the power constraint; and selecting all target power supply entities participating in the current power service to construct an adjustable power supply entity set.

Specifically, in S8, there are two matching situations, and when the power consumption entity is dominant, that is, when the power consumption entity selects the corresponding power supply entity, the method includes the following steps:

In this embodiment, target power supply entities with the same discharge power on each time scale are sequentially screened out to construct a first flow container, and it is known that the boundary of the first flow container is the maximum discharge power on the time scale; because different electricity prices have different excitation effects on different electricity consumption entities, the time-sharing time scales are prioritized to obtain a first optimal calibration time table, and it can be understood that the electricity consumption entity with better electricity consumption behavior (user activity) is preferentially scheduled to a time scale interval with lower electricity price for charging behavior, so that the electricity consumption entity can be effectively excited to normalize the own electricity consumption behavior (for example, the single charging electric quantity can be improved, the time interval of the lifting time can be shortened, and the user activity can be improved); and the flow boundary of the first flow container is used as a charging constraint condition, the target power consumption entity of the discharging power is matched, and finally, a corresponding power supply entity and a charging time scale interval are selected for each power consumption entity, so that the power consumption behavior of the power entity is indirectly standardized and positively stimulated while the fine management and the optimal control of the power consumption behavior are realized.

When the power supply entity is dominant, that is, the power supply entity selects the corresponding power consumption entity, the method comprises the following steps:

In this embodiment, target power consumption entities with the same charging power on each time scale are sequentially screened out to construct a second flow container, and it is known that the boundary of the second flow container is the maximum charging power on the time scale; because different electricity prices have different excitation effects on different power supply entities, the time-sharing time scales are prioritized to obtain a second optimal calibration time table, and it can be understood that the power supply entities with better electricity consumption behavior (user activity) are preferentially scheduled to a time scale interval with higher electricity prices to perform discharging behavior, and because the power supply entities possibly belong to different service providers, the service policies of the different service providers are different, the service providers can be effectively stimulated to optimize the own electricity consumption behavior (for example, the single power supply electric quantity can be improved, the power supply time interval can be shortened, and the user activity can be improved); and the flow boundary of the second flow container is used as a power supply constraint condition, a target power supply entity of discharge power is matched, and a corresponding power consumption entity and a discharge time scale interval are selected for each power consumption entity, so that the power consumption behavior of the power entity is indirectly standardized and positively stimulated while the fine management and the optimal control of the power consumption behavior are realized.

Further, the current limiting algorithm is one of a sliding window current limiting algorithm, a leaky bucket current limiting algorithm and a token bucket current limiting algorithm.

In this embodiment, in the daily charging service, since the charging of the electric vehicle has randomness, when there may be a sudden situation such as a peak period of electricity consumption, the charging amount is greatly increased, and in order to ensure the safety of the electric power operation, the electricity consumption behavior of the electric entity with high charging and discharging priority (high activity level) is ensured, so that current limitation is required; for example, according to the maximum discharge power of the first flow container or the maximum charge power of the second flow container, a current limiting algorithm may be adopted, when the charge power of all the target power consumption entities is greater than the maximum discharge power, the current target power consumption entities may be sequentially arranged to the time scale interval of the next priority for performing the charging action, and similarly, when the discharge power of all the target power supply entities is greater than the maximum charge power, the current target power supply entities may be sequentially arranged to the time scale interval of the next priority for performing the discharging action, so as to ensure the stability of the charging and discharging actions.

It can be understood that, assuming that the priority of the time scale interval is T1> T2> T3, when the maximum discharge power of the first flow container is P1 in the time scale interval T1; the maximum discharge power of the first flow container is P2 in a time scale interval T2; the maximum discharge power of the first flow container is P3 in a time scale interval T3; when the charging power of all the target power consumption entities in the time scale interval T1 is greater than P1, performing matched charging according to the priority of the target power consumption entities, for example, preferably selecting a consumption entity set [ a1, a3, a6, a8, a2]; the sum of the powers of the power consuming entities a1, a3, a6, a8 is smaller than P1; the sum of the powers of the power consuming entities a1, a3, a6, a8, a2 is larger than P1; the power consumption entity allowed to be charged in the time scale interval T1 is [ a1, a3, a6, a8], and based on the current limiting principle, the time scale interval allowed to be charged in the power consumption entity a2 is T2; another situation that may exist is: the sum of the powers of the power consuming entities a1, a3, a6 is smaller than P1; the power of the power consuming entities a1, a3, a6, a8 is larger than P1, and the power of the power consuming entities a1, a3, a6, a2 is smaller than P1; the power consumption entity allowed to be charged in the time scale interval T1 is [ a1, a3, a6, a2], and based on the current limiting principle, the time scale interval allowed to be charged in the power consumption entity a8 is T2; similarly, when the maximum discharge power of the second flow container is P2 in the time scale interval T1, the selection of the power supply entity is the same as the above manner according to the current limiting algorithm, and will not be described again here.

Embodiment two:

the embodiment of the invention also provides a technical scheme of the user portrait construction system for the complex electricity behavior, which comprises the following steps:

In this embodiment, the characteristic data of each power consumption entity is first analyzed, the characteristic data affecting the consumption behavior of the power consumption entity is obtained as a first effective index, and a representation of the power consumption entity can be constructed based on the first effective index, so that the characteristic variables of the power consumption entity are output result data based on a logistic regression model, and the result is divided into two types: an inactive power consuming entity and an active power consuming entity; wherein the inactive power consuming entity and the active power consuming entity are partitioned based on a charging probability behavior of the power consuming entity; similarly, the characteristic data of each power supply entity is analyzed, the characteristic data affecting the service behavior of the power supply entity is obtained to serve as a second effective index, a power supply entity portrait can be constructed based on the second effective index, the characteristic variables of the power supply entity are result data output based on a logistic regression model, and the result is divided into two types: an inactive power supply entity and an active power supply entity; wherein the inactive power supply entity and the active power supply entity are divided based on the power supply probability of the power consuming entity; further, the consumption path of the power consumption entity is analyzed, so that the consumption habit of the power consumption entity can be further analyzed, and the association relationship between the power consumption entity and the power supply entity is established; similarly, the service path of the power supply entity is analyzed, so that the service habit of the power supply entity can be further analyzed, and the association relationship between the power supply entity and the power consumption entity is established; providing reference data for subsequent resource pairing; then analyzing the adjustable power supply allowance and the electric energy demand on each time-sharing time scale, and selecting the optimal power supply entity and power consumption entity combination based on the electric power supply and demand relation; finally, considering the problem of unbalance of power supply and power demand on a time-sharing time scale, calibrating a chargeable time domain based on a current limiting algorithm, and acquiring power consumption behavior association images of each entity in an adjustable power supply entity set and an adjustable power consumption entity set based on a calibration result, so that each power supply entity and each power supply entity can form an optimal power supply and demand combination, and the management and control efficiency and stability of a power system are further improved while the fine management and optimization control of the power consumption behaviors are realized.

Embodiment III:

the technical scheme provided by the embodiment of the application is that the electronic equipment comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the user portrait construction method based on the complex electricity consumption behavior based on the current limiting algorithm when calling the computer program in the memory.

Embodiment four:

the technical scheme provided by the embodiment of the application is as follows: a storage medium having stored therein computer executable instructions which, when loaded and executed by a processor, implement the steps of the complex electricity usage behavior user portrayal construction method based on a current limiting algorithm as described.

From the foregoing description of the embodiments, it will be appreciated by those skilled in the art that, for convenience and brevity of description, only the above-described division of functional modules is illustrated, and in practical application, the above-described functional allocation may be implemented by different functional modules according to needs, i.e. the internal structure of a specific apparatus is divided into different functional modules to implement all or part of the functions described above.

In the embodiments provided in the present application, it should be understood that the disclosed structures and methods may be implemented in other manners. For example, the embodiments described above with respect to structures are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another structure, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via interfaces, structures or units, which may be in electrical, mechanical or other forms.

The units described as separate parts may or may not be physically separate, and the parts shown as units may be one physical unit or a plurality of physical units, may be located in one place, or may be distributed in a plurality of different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be essentially or a part contributing to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, including several instructions for causing a device (may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read Only Memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are preferred embodiments of the method and system for constructing a user portrait based on a current limiting algorithm, and are not intended to limit the scope of the present invention, which includes but is not limited to the present embodiments, and equivalent changes in shape and structure according to the present invention are all within the scope of the present invention.

Claims

1. The method for constructing the user portraits of the complex electricity utilization behaviors based on the current limiting algorithm is characterized by comprising the following steps of: the method comprises the following steps:

s8, calibrating the chargeable time domain based on a current limiting algorithm, and acquiring electricity consumption behavior association figures of all entities in the adjustable power supply entity set and the adjustable electricity consumption entity set based on a calibration result;

the method includes the steps of obtaining power consumption entity characteristic data on a long-time domain of a station area, calculating first information value degrees between characteristic indexes and first characteristic variables in power consumption entities, taking the characteristic indexes with the first information value degrees larger than a set association threshold H1 as first effective indexes, and constructing power consumption entity portraits of the characteristic variables based on the first effective indexes, and comprises the following steps:

s14, constructing a power consumption entity portrait based on the charging probability of the power consumption entity and the association coefficient of the corresponding first effective index;

the method includes the steps that power supply entity characteristic data on a long-time domain of a station area are obtained, a second information value degree between each characteristic index and a second characteristic variable in a power supply entity is calculated, the characteristic index with the second information value degree being larger than a set association threshold H2 is used as a second effective index, and a power supply entity portrait of the characteristic variable is constructed based on the second effective index, and the method comprises the following steps:

s24, constructing a power supply entity portrait based on the power supply probability of the power supply entity and the association coefficient of the corresponding second effective index;

the consumption path based on the power consumption entity constructs a first association degree set with each power supply entity in the platform area; integrating the first association degree set based on the service priority of the power supply entity to obtain a preferred service entity set, comprising the following steps:

s31, acquiring a corresponding target power supply entity based on a link relation between a power consumption entity and the power supply entity in a long time domain, and constructing a first association degree set;

s33, sorting all target power supply entities in the first association degree set from large to small based on service priority to obtain a preferred service entity set;

The service path based on the power supply entity constructs a second association degree set with each power consumption entity in the platform area; integrating the second association degree set based on the consumption priority of the power consumption entity to obtain a preferred consumption entity set, comprising the following steps:

s41, acquiring a corresponding target power consumption entity based on a link relation between a power supply entity and the power consumption entity in a long time domain, and constructing a second association degree set;

s43, sorting all target power consumption entities in the second association degree set from large to small based on the consumption priority to obtain a preferred consumption entity set;

the current limiting algorithm is based on calibrating a chargeable time domain, and the power consumption behavior association image of each entity in the adjustable power supply entity set and the adjustable power consumption entity set is obtained based on a calibration result, and the method comprises the following steps:

2. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the first linking degree L1 is calculated according to the following formula:

L1=P1/T1

3. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the second link degree L2 is calculated according to the formula:

L2=P2/T2

4. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

The method for acquiring the adjustable power supply margin and the electric energy demand on the time-sharing time scale comprises the following steps:

5. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the method for obtaining the adjustable power consumption entity set based on the power demand and the preferable power consumption entity set comprises the following steps:

6. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the adjustable power supply entity set is obtained based on the adjustable power supply margin and the preferable service entity set, and comprises the following steps:

7. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the method comprises the steps of calibrating a chargeable time domain based on a current limiting algorithm, acquiring electricity consumption behavior association figures of each entity in an adjustable power supply entity set and an adjustable power consumption entity set based on a calibration result, and further comprising the following steps:

8. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as defined in claim 1 or 7, wherein the method comprises the following steps:

the flow limiting algorithm is one of a sliding window flow limiting algorithm, a leaky bucket flow limiting algorithm and a token bucket flow limiting algorithm.

9. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the power consumption entity state information includes: inactive power consuming entities and active power consuming entities.

10. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the power consumption entity attribute information includes: charging period, charging duration, charging frequency, charging power, charging day, single charge power distribution, and time interval for lifting.

11. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the power supply entity state information includes: an inactive power entity and an active power entity.

12. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the power supply entity attribute information includes: the power supply system comprises a power supply period, a power supply duration, a power supply frequency, a power supply power, a power supply day, a single power supply electric quantity distribution and a power supply time interval.

13. The method for constructing the user portrayal of the complex electricity behavior based on the current limiting algorithm as recited in claim 1, wherein the method comprises the following steps:

the public variable liability characteristic includes: the public transformer load ratios corresponding to the number of the charging piles and the public transformer load ratios corresponding to different seasons.

14. The complicated electricity consumption behavior user figure construction system is suitable for the complicated electricity consumption behavior user figure construction method based on the current limiting algorithm as claimed in any one of claims 1 to 13, and is characterized in that: comprises the following steps:

and a second integration module: constructing a second association degree set with each power supply entity in the platform area based on the service path of the power consumption entity; integrating the second association degree set based on the consumption priority of the power consumption entity to obtain a preferred consumption entity set;

15. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor, when invoking the computer program in the memory, implements the steps of the current limiting algorithm-based complex electricity usage behavior user representation construction method according to any of claims 1 to 13.

16. A storage medium having stored therein computer executable instructions which, when loaded and executed by a processor, implement the steps of the current limiting algorithm based complex electricity usage behavior user portrayal construction method according to any one of claims 1 to 13.